Deployment

Loading...

From the course by IBM

Data Science Methodology

5024 ratings

IBM

Data Science Methodology

5024 ratings

Course 3 of 9 in the Specialization IBM Data Science Professional Certificate

Despite the recent increase in computing power and access to data over the last couple of decades, our ability to use the data within the decision making process is either lost or not maximized at all too often, we don't have a solid understanding of the questions being asked and how to apply the data correctly to the problem at hand. This course has one purpose, and that is to share a methodology that can be used within data science, to ensure that the data used in problem solving is relevant and properly manipulated to address the question at hand. Accordingly, in this course, you will learn: - The major steps involved in tackling a data science problem. - The major steps involved in practicing data science, from forming a concrete business or research problem, to collecting and analyzing data, to building a model, and understanding the feedback after model deployment. - How data scientists think! LIMITED TIME OFFER: Subscription is only $39 USD per month for access to graded materials and a certificate.

From the lesson

From Deployment to Feedback

In this module, you will learn about what happens when a model is deployed and why model feedback is important. Also, by completing a peer-reviewed assignment, you will demonstrate your understanding of the data science methodology by apply it to a problem that you define.

Course Summary3:12

Meet the Instructors

Alex Aklson
Ph.D., Data Scientist
IBM Developer Skills Network
Polong Lin
Data Scientist
IBM Developer Skills Network

Welcome to Data Science Methodology 101 From Deployment to Feedback - Deployment!

While a data science model will provide an answer, the key to making the answer relevant

and useful to address the initial question, involves getting the stakeholders familiar

with the tool produced.

In a business scenario, stakeholders have different specialties that will help make

this happen, such as the solution owner, marketing, application developers, and IT administration.

Once the model is evaluated and the data scientist is confident it will work, it is deployed

and put to the ultimate test.

Depending on the purpose of the model, it may be rolled out to a limited group of users

or in a test environment, to build up confidence in applying the outcome for use across the board.

So now, let's look at the case study related to applying Deployment"

In preparation for solution deployment, the next step was to assimilate the knowledge

for the business group who would be designing and managing the intervention program to reduce

readmission risk.

In this scenario, the business people translated the model results so that the clinical staff

could understand how to identify high-risk patients and design suitable intervention

actions.

The goal, of course, was to reduce the likelihood that these patients would be readmitted within

30 days after discharge.

During the business requirements stage, the Intervention Program Director and her team

had wanted an application that would provide automated, near real-time risk assessments

of congestive heart failure.

It also had to be easy for clinical staff to use, and preferably through browser-based

application on a tablet, that each staff member could carry around.

This patient data was generated throughout the hospital stay.

It would be automatically prepared in a format needed by the model and each patient would

be scored near the time of discharge.

Clinicians would then have the most up-to-date risk assessment for each patient, helping

them to select which patients to target for intervention after discharge.

As part of solution deployment, the Intervention team would develop and deliver training for

the clinical staff.

Also, processes for tracking and monitoring patients receiving the intervention would

have to be developed in collaboration with IT developers and database administrators,

so that the results could go through the feedback stage and the model could be refined over

time.

This map is an example of a solution deployed through a Cognos application.

In this case, the case study was hospitalization risk for patients with juvenile diabetes.

Like the congestive heart failure use case, this one used decision tree classification

to create a risk model that would serve as the foundation for this application.

The map gives an overview of hospitalization risk nationwide, with an interactive analysis

of predicted risk by a variety of patient conditions and other characteristics.

This slide shows an interactive summary report of risk by patient population within a given

node of the model, so that clinicians could understand the combination of conditions for

this subgroup of patients.

And this report gives a detailed summary on an individual patient, including the patient's

predicted risk and details about the clinical history, giving a concise summary for the

doctor.

This ends the Deployment section of this course.

Thanks for watching!

Explore our Catalog

Join for free and get personalized recommendations, updates and offers.

Coursera provides universal access to the world’s best education, partnering with top universities and organizations to offer courses online.

© 2019 Coursera Inc. All rights reserved.

Download on the App Store

Get it on Google Play